© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6126
    Prev
    Next
    INDEX
    Explanations

    foreign languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     некоторое
    0.71
    новой
    0.68
    該
    0.66
    ясь
    0.64
     एकदा
    0.62
    новых
    0.61
     временем
    0.61
    новый
    0.61
    此
    0.59
    出て
    0.59
    POSITIVE LOGITS
    을
    1.13
     را
    1.03
    를
    1.01
    ını
    0.94
    들을
    0.90
     İç
    0.88
     को
    0.87
    ının
    0.84
     İş
    0.83
    ına
    0.82
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.